The boiling crisis or critical heat flux (CHF) is a very critical constraint for any heat-flux-controlled boiling system. The existing methods (physical models and empirical correlations) offer a specific interpretation of the boiling phenomenon, as many of these correlations are considerably influenced by operational variables and surface morphologies. A generalized correlation is virtually unavailable. In this study, more physical mechanisms are incorporated to assess CHF of surfaces with micro- and nano-scale roughness subject to a wide range of operating conditions and working fluids. The CHF data is also correlated by using the Pearson, Kendal, and Spearman correlations to evaluate the association of various surface morphological features and thermophysical properties of the working fluid. Feature engineering is performed to better correlate the inputs with the desired output parameter. The random forest optimization (RF) is used to provide the optimal hyper-parameters to the proposed interpretable correlation and experimental data. Unlike the existing methods, the proposed method is able to incorporate more physical mechanisms and relevant parametric influences, thereby offering a more generalized and accurate prediction of CHF (R² = 0.971, mean squared error = 0.0541, and mean absolute error = 0.185).

Extensive amount of research on additively manufactured (AM) lattice structures has been made to develop a generalized model that can interpret how strongly operational variables affect mechanical properties. However, the currently used techniques such as physics models and multi-physics simulations provide a specific interpretation of those qualities, and are not general enough to assess the mechanical properties of AM lattice structures of different topologies produced on different materials via several fabrication methods. To tackle this problem, this study develops an optimal deep learning (DL) model based on more than 4000 data points, which has been optimized by analyzing three different hyper-parameters optimization schemes including gradient boost regression trees (GBRT), gaussian process (GP), and random forest (RF) with different data distribution schemes such as normal distribution, nth root transformation, and robust scaler. With the robust scaler and nth root transformation, the accuracy of the model increases from R² = 0.85 (for simple distribution) to R² = 0.94 and R² = 0.88, respectively. After feature engineering and data correlation, the stress, unit cell size, total height, width, and relative density are chosen to be the input parameters to model the strain. The optimal DL model is able to predict the strain of different topologies of lattices (such as circular, octagonal, Gyroid, truncated cube, Truncated cuboctahedron, Rhombic do-decahedron, and many others) with decent accuracy (R² = 0.936, MAE = 0.05, and MSE = 0.025). The parametric sensitivity analysis and explainable artificial intelligence (by using DeepSHAP library) based insights confirm that stress is the most sensitive input to the strain followed by the relative density from the modeling perspective of the AM lattices. The findings of this study would be helpful for the industry and the researchers to design AM lattice structures of different topologies for various engineering applications.